index / pabloirracional/jev-evaluation
jev-evaluation
How far can a small model go? Testing TypeSafe's Jev on 1,352 cases against large LLMs: 98% accuracy, ~200x cheaper than Claude Opus 5.5
Research and EvalsVerificationListedPython
Repository
Stars0
LanguagePython
LicenseMIT
Created2026-09-24
Last pushed2026-09-24
Officialno
Judgment
Genuine Jev project0.96
gate 0.5
Uses Jev at runtime0.46
Is a meta list0.05
Is a reimplementation0.07
Quality scales
Substance1.98 / 3
gate 0.5
Docs2.55 / 3
Novelty2.88 / 3
Composite score0.80
Category distribution
Research and Evals1.00
Learning0.00
Applications0.00
Agent and Dev Tooling0.00
Other0.00
Games and Simulation0.00
Integrations0.00
SDKs and Clients0.00
Assigned categoryResearch and Evals
Category probability1.00
Category confidence1.00
PatternVerification
Pattern confidence0.60
Curation
StatusListed
Reasongate passed
README pickno
Overridenone
Sources
- search:jev in:name,description,readme created:2026-09-24
Provenance
Modeljev-1.13.0
Question setv2
Judged at2026-09-27 11:43 UTC